- 著者
- Masato Koda Hiroyuki Okano
- 出版者
- The Operations Research Society of Japan
- 雑誌
- 日本オペレーションズ・リサーチ学会論文誌 (ISSN:04534514)
- 巻号頁・発行日
- vol.43, no.4, pp.469-485, 2000 (Released:2017-06-27)
- 参考文献数
- 17
- 被引用文献数
- 4 4
A new stochastic learning algorithm using Gaussian white noise sequence, referred to as Subconscious Noise Reaction (SNR), is proposed for a class of discrete-time neural networks with time-dependent connection weights. Unlike the back-propagation-through-time (BTT) algorithm, SNR does not require the synchronous transmission of information backward along connection weights, while it uses only ubiquitous noise and local signals, which are correlated against a single performance functional, to achieve simple sequential (chronologically ordered) updating of connection weights. The algorithm is derived and analyzed on the basis of a functional derivative formulation of the gradient descent method in conjunction with stochastic sensitivity analysis techniques using the variational approach.